AI system
- System
-
FamilySearch Full-Text Search (handwriting recognition and OCR); Transkribus (READ-COOP SCE)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
FamilySearch International; READ-COOP SCE
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Handwriting-recognition models applied to digitized record images. Indexing of recognized text for search.
- Human oversight
-
Not assessed
- Relation to AI
-
Handwriting-recognition models produce the searchable text in both systems. The only cited sources are the makers' own (the Church newsroom for FamilySearch, the Transkribus site). They give capability and volume claims but no specific verified finding.
- AI contribution
-
Handwriting-recognition models produce the searchable text in both systems. The only cited sources are the makers' own (the Church newsroom for FamilySearch, the Transkribus site). They give capability and volume claims but no specific verified finding.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
200 million pages deciphered
- Category
-
Improved Knowledge Discovery
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
200 million pages deciphered
- Comparison
-
Not assessed
- Results
-
200 million pages deciphered
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: FamilySearch International; READ-COOP SCE. Operator: FamilySearch Labs; archives and research projects using Transkribus (University of Georgia, Archion).
- Jurisdictions
-
Benefit: Global (FamilySearch users; European and US archives). Developer:
United States. Operator: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Recognition accuracy adequate for names and places. Independent documentation of specific findings (absent).
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
13 January 2026. FamilySearch's year-end review for 2025 (reproduced 9 January 2026) says Full-Text Search was fully released from FamilySearch Labs in 2025 alongside 2.2 billion newly searchable names and images, and its 2026 plans (reported 13 January 2026) are to extend the handwriting-reading technology to additional languages.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0279-source-0001–0004
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer, Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
People: No documented individual discovery or reunion. Organizations: Project volumes are reported only by the vendors. Society: No attributable event.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The makers' claim
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Genealogy; archives. Family historians and archival researchers.
- Purpose
-
Make handwritten historical records searchable by converting images to text with AI handwriting recognition
- Dates
-
Date basis unassessed: 2025 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: e70822d2b286…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
6 revisions. Latest: 21 October 2026.
Sources
-
Press release Developer
Newsroom of The Church of Jesus Christ of Latter-day Saints, 2 Jan 2025
FamilySearch can convert an image of text into a machine-readable text format, allowing users to search the full text of the records.
-
Press release Developer
Transkribus website
turns centuries of handwriting into text you can search, study, and share.
transcribed 20,000 pages in two months
-
Other Independent author
Seaver R (13 Jan 2026). What to Expect from FamilySearch in 2026: Emerging Technologies Will Help Fuel New Family Discoveries. Genea-Musings (reproducing FamilySearch's announcement).